Latent Space Energy-Based Model of Symbol-Vector Coupling for Text
Generation and Classification
Bo Pang 1 Ying Nian Wu 1
Abstract most of prior methods focus on the improvement of text
generation quality such as fluency and diversity. Besides
We propose a latent space energy-based prior
the quality, the interpretability or controllability of text gen-
model ...


雷达卡




京公网安备 11010802022788号







